cardiffnlp / timelms
TimeLMs: Diachronic Language Models from Twitter
☆107Updated 11 months ago
Alternatives and similar repositories for timelms:
Users that are interested in timelms are comparing it to the libraries listed below
- Google's BigBird (Jax/Flax & PyTorch) @ 🤗Transformers☆48Updated last year
- A python package for benchmarking interpretability techniques on Transformers.☆213Updated 4 months ago
- ☆74Updated 3 years ago
- Seahorse is a dataset for multilingual, multi-faceted summarization evaluation. It consists of 96K summaries with human ratings along 6 q…☆86Updated 11 months ago
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆93Updated 2 years ago
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆74Updated 2 years ago
- Collection of NLP model explanations and accompanying analysis tools☆145Updated last year
- A python package to run inference with HuggingFace language and vision-language checkpoints wrapping many convenient features.☆26Updated 5 months ago
- This repository contains materials for the SIGIR 2022 tutorial on opinion summarization.☆34Updated 2 years ago
- A monolingual and cross-lingual meta-embedding generation and evaluation framework☆80Updated 2 years ago
- Multi-task modelling extensions for huggingface transformers☆20Updated last year
- This repository contains the code for "Generating Datasets with Pretrained Language Models".☆187Updated 3 years ago
- ☆155Updated 7 months ago
- Creating class-based TF-IDF matrices☆82Updated 2 years ago
- A curated list of awesome datasets with human label variation (un-aggregated labels) in Natural Language Processing and Computer Vision, …☆80Updated 10 months ago
- Code & Data for Comparative Opinion Summarization via Collaborative Decoding (Iso et al; Findings of ACL 2022)☆21Updated last year
- As good as new. How to successfully recycle English GPT-2 to make models for other languages (ACL Findings 2021)☆48Updated 3 years ago
- This repository contains the code for the paper 'PARM: Paragraph Aggregation Retrieval Model for Dense Document-to-Document Retrieval' pu…☆40Updated 3 years ago
- Contrastive Fact Verification☆71Updated 2 years ago
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval☆28Updated 2 years ago
- Augmenty is an augmentation library based on spaCy for augmenting texts.☆151Updated 8 months ago
- Apps built using Inspired Cognition's Critique.☆58Updated last year
- The official code for PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization☆156Updated 2 years ago
- A library for parameter-efficient and composable transfer learning for NLP with sparse fine-tunings.☆71Updated 6 months ago
- Code for our WOAH@ACL 2021 Paper on Data Integration for Toxic Comment Classification: Making More Than 40 Datasets Easily Accessible in …☆27Updated 3 years ago
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆70Updated 11 months ago
- [DEPRECATED] Adapt Transformer-based language models to new text domains☆86Updated 11 months ago
- An instruction-based benchmark for text improvements.☆140Updated 2 years ago
- The NewSHead dataset is a multi-doc headline dataset used in NHNet for training a headline summarization model.☆37Updated 3 years ago
- A multilingual version of MS MARCO passage ranking dataset☆143Updated last year